<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="arias-russi-etal-2025-multi">
    <titleInfo>
        <title>A Multi-Agent Framework with Diagnostic Feedback for Iterative Plain Language Summary Generation from Cochrane Medical Abstracts</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Felipe</namePart>
        <namePart type="family">Arias Russi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Carolina</namePart>
        <namePart type="family">Salazar Lara</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ruben</namePart>
        <namePart type="family">Manrique</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Fourth Workshop on Text Simplification, Accessibility and Readability (TSAR 2025)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Matthew</namePart>
            <namePart type="family">Shardlow</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Fernando</namePart>
            <namePart type="family">Alva-Manchego</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kai</namePart>
            <namePart type="family">North</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Regina</namePart>
            <namePart type="family">Stodden</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Horacio</namePart>
            <namePart type="family">Saggion</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nouran</namePart>
            <namePart type="family">Khallaf</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Akio</namePart>
            <namePart type="family">Hayakawa</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Suzhou, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-176-6</identifier>
    </relatedItem>
    <abstract>Plain Language Summaries PLS improve health literacy and enable informed healthcare decisions but writing them requires domain expertise and is time-consuming. Automated methods often prioritize efficiency over comprehension and medical documents unique simplification requirements challenge generic solutions. We present a multi-agent system for generating PLS using Cochrane PLS as proof of concept. The system uses specialized agents for information extraction writing diagnosis and evaluation integrating a medical glossary and statistical analyzer to guide revisions. We evaluated three architectural configurations on 100 Cochrane abstracts using six LLMs both proprietary and open-source. Results reveal model-dependent trade-offs between factuality and readability with the multi-agent approach showing improvements for smaller models and providing operational advantages in control and interpretability.</abstract>
    <identifier type="citekey">arias-russi-etal-2025-multi</identifier>
    <location>
        <url>https://aclanthology.org/2025.tsar-1.6/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>87</start>
            <end>104</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T A Multi-Agent Framework with Diagnostic Feedback for Iterative Plain Language Summary Generation from Cochrane Medical Abstracts
%A Arias Russi, Felipe
%A Salazar Lara, Carolina
%A Manrique, Ruben
%Y Shardlow, Matthew
%Y Alva-Manchego, Fernando
%Y North, Kai
%Y Stodden, Regina
%Y Saggion, Horacio
%Y Khallaf, Nouran
%Y Hayakawa, Akio
%S Proceedings of the Fourth Workshop on Text Simplification, Accessibility and Readability (TSAR 2025)
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-176-6
%F arias-russi-etal-2025-multi
%X Plain Language Summaries PLS improve health literacy and enable informed healthcare decisions but writing them requires domain expertise and is time-consuming. Automated methods often prioritize efficiency over comprehension and medical documents unique simplification requirements challenge generic solutions. We present a multi-agent system for generating PLS using Cochrane PLS as proof of concept. The system uses specialized agents for information extraction writing diagnosis and evaluation integrating a medical glossary and statistical analyzer to guide revisions. We evaluated three architectural configurations on 100 Cochrane abstracts using six LLMs both proprietary and open-source. Results reveal model-dependent trade-offs between factuality and readability with the multi-agent approach showing improvements for smaller models and providing operational advantages in control and interpretability.
%U https://aclanthology.org/2025.tsar-1.6/
%P 87-104

Markdown (Informal)

[A Multi-Agent Framework with Diagnostic Feedback for Iterative Plain Language Summary Generation from Cochrane Medical Abstracts](https://aclanthology.org/2025.tsar-1.6/) (Arias Russi et al., TSAR 2025)

• A Multi-Agent Framework with Diagnostic Feedback for Iterative Plain Language Summary Generation from Cochrane Medical Abstracts (Arias Russi et al., TSAR 2025)

ACL

• Felipe Arias Russi, Carolina Salazar Lara, and Ruben Manrique. 2025. A Multi-Agent Framework with Diagnostic Feedback for Iterative Plain Language Summary Generation from Cochrane Medical Abstracts. In Proceedings of the Fourth Workshop on Text Simplification, Accessibility and Readability (TSAR 2025), pages 87–104, Suzhou, China. Association for Computational Linguistics.